Towards Efficient Threat Intelligence Instruction Tuning via Quality-Aware and Optimal Transport-Guided Data Selection
CTI-TDS selects compact, high-quality instruction data for threat-intelligence model tuning.
Stories per day · 30 days
2 RSS
18 stories, newest first · one card per story
Stories tagged #optimal-transport
Rethinking Projector Training in Multimodal LLMs
PORTAL initializes multimodal projectors from summary statistics and matches caption-trained alignment without paired data.
Scaling Online Optimal Transport Minibatches for Flow Matching
A scalable online entropic OT method stabilizes flow-matching training with larger source-target couplings.
Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian Residuals
Double-Stitch learns Wasserstein Lagrangian population dynamics simulation-free, training 4-14x faster than solver-based WLM while covering periodic dynamics.
Cost-augmented Schrödinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
Graph Schrödinger bridges with state costs are solved exactly via a Feynman-Kac tilt, with no learning.
Discrete Wasserstein Flows for One-Step Generative Modeling
Discrete Wasserstein flows enable one-step generative modeling on finite state spaces.
OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport
OTRetarget jointly retargets humanoid and object motion from human demos using entropic optimal transport.
Unifying Distributional Training for One-Step Visual Generation
MGFlow unifies one-step visual training and beats FD-Loss on ImageNet and four-step FLUX.2.
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
ColNanoVDR distills multi-vector document retrievers into 149M students that keep 95% NDCG@5 and run up to 26x faster.
Sliced Orlicz-Wasserstein
A paper proposes sliced Orlicz-Wasserstein distance, proving metric properties and cheaper estimation than Orlicz-Wasserstein.
Aligning One-Step Generative Models with Reward-Weighted Transport Distillation
RWTD post-trains one-step generators, raising SANA Sprint GenEval from 0.73 to 0.80.
Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
Paper proves parametric rates for semi-discrete entropic optimal transport, including barycentric projection and Sinkhorn-EM.
Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
Review connects control theory, optimal transport, probabilistic inference, thermodynamics, and machine learning via free-energy optimization under constraints.
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
OptiFlow learns one-step multimodal flow policies for offline RL via state-wise entropic optimal transport, avoiding critic overestimation and mode collapse.
CMA-OT: Hierarchical Expert Supervision for Dance-to-Music Generation
CMA-OT aligns a music generator's latent features with hierarchical expert representations via curriculum learning and scale-aware optimal transport, improving dance-to-music quality.
General Quantification of Covariate and Concept Shifts
Paper proposes γ*-concept shifts via entropic optimal transport, deriving estimable generalization bounds unifying covariate and concept shift under distribution shift.
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Researchers introduce model-aware diffusion schedules via fiberwise optimal transport, cutting flow-matching FID on CIFAR-10 by 38.6% at 16 function evaluations.
Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics
Researchers model curriculum learning as Wasserstein transport over difficulty distributions, finding curriculum benefits are strongly task- and budget-dependent with no dominant strategy.